pull-requests

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to poll and act on GitHub PR review threads and Codex comments (e.g., ./scripts/check_codex_comments.sh, ./scripts/resolve_pr_comment.sh, and the required PR readiness loop in SKILL.md), which are user-generated, potentially public review comments that the agent must read and act upon, so untrusted third-party content can influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 08:11 PM